NVIDIA-Nemotron-3.5-Lightning-30B-A3B-NVFP4

NVIDIA

**Model Developer:** NVIDIA Corporation **Model Dates:** December 2025 - May 2026 **Data Freshness:** * The pre-training data has a cutoff date of September 2025. * The post-training data has a cutoff date of May 2026. NVIDIA Nemotron™ is a family of open models with open weights, training data, and recipes, delivering leading efficiency and accuracy for building specialized AI agents. **NVIDIA-Nemotron-3.5-Lightning-30B-A3B-NVFP4** is a large language model (LLM) trained by NVIDIA. The model employs a hybrid **Mixture-of-Experts** architecture, utilizing interleaved Mamba-2 and MoE layers, along with select Attention layers. The Lightning 3.5 model is released alongside a number of speculative decoding methods for faster text generation. The model has **3B active parameters** and **30B parameters in total**. This model is ready for commercial use. To get quickly started on DGX Spark (GB10) you can use the following command. Grab the model: export MODEL_CKPT=nvidia/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-NVFP4 export DSPARK_CKPT=nvidia/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-NVFP4-DSpark Run it with vLLM — this recipe uses DSpark speculative decoding, tuned for DGX Spark. (vLLM version: `vllm/vllm-openai:v0.27.1`) vllm serve --model $MODEL_CKPT \ --moe-backend marlin \ --kv-cache-dtype fp8 \ --enable-prefix-caching \ --gpu-memory-utilization 0.85 \ --speculative_config.num_speculative_tokens 3 \ --mamba-backend flashinfer \ --mamba-cache-mode align \ --reasoning-parser nemotron_v3 \ --speculative_config.model $DSPARK_CKPT \ --tool-call-parser qwen3_coder \ --enable-auto-tool-choice **Validated context:** 1M tokens (default). For more details on how to deploy and use the model — see the [Quick Start Guide](#quick-start-guide) below! **Governing Download Terms:** Use of this model is governed by the [OpenMDW-1.1 model license](https://openmdw.ai/license/1-1/). We evaluated our model on the following benchmarks: Accuracy numbers measured by NVIDIA under a consistent harness (NeMo Gym / Nemo Evaluator SDK); they may differ from vendors' self-reported numbers. For reproducibility, the evaluation recipes, installation instructions, and commands for NVIDIA Nemotron 3.5 Lightning were collected and published in [NeMo Gym](https://github.com/NVIDIA-NeMo/Gym/tree/main/nemotron_recipes/lightning-3.5/reproducibility.md). The reported results cover the release evaluation suite, including knowledge and reasoning, instruction following, coding, agentic, tool-use, and long-context. Most evaluations use NeMo Gym-native harnesses while a small subset, including SWE-Bench and Terminal-Bench, used [NeMo Evaluator](https://github.com/NVIDIA-NeMo/Evaluator) natively. The published recipes specify the benchmark-specific containers, prompts, inference parameters, parser configurations, and scoring settings used to produce the results. > These numbers were measured with and apply to the official [NVFP4 checkpoint](https://huggingface.co/nvidia/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-NVFP4) Additional harness-level coding-agent results for SWE-Bench Verified and Terminal-Bench 2.1 are shown below. NVIDIA-Nemotron-3.5-Lightning-30B-A3B-NVFP4 is a general purpose reasoning and chat model intended to be used in English and coding languages. Other non-English languages (Spanish, French, German, Italian, Japanese) are also supported. Intended for developers designing AI Agent systems, chatbots, RAG systems, and other AI-powered applications. Also suitable for typical instruction-following tasks. [Hugging Face](https://huggingface.co/nvidia/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-NVFP4) — 08/11/2026 - **Architecture Type:** Mixture-of-Experts Hybrid (Mamba + Transformer) - **Network Architecture:** Nemotron-3-Lightning + Multi-Token Prediction (MTP) - **Number of model parameters:** 30B Total / 3B Active The model was pre-trained with over 20T tokens and supports up to 1M context length. The pre-training phase used an NVFP4 recipe. The model includes **Multi-Token Prediction (MTP)** layers, which predict multiple future tokens to provide richer training signals. Stage 1: Pre-Training * NVIDIA-Nemotron-3.5-Lightning-30B-A3B-NVFP4 model was pre-trained using an NVFP4 recipe with crawled and synthetic code, math, science, and general knowledge data. * Software used for pre-training: [Megatron-LM](https://github.com/NVIDIA/Megatron-LM) Stage 2: Continued Pre-Training for Multi-Token Prediction (MTP) * The model underwent a continued pre-training phase to train its **Multi-Token Prediction (MTP)** layers. In this stage, MTP heads learn to predict multiple future tokens, providing richer training signals to the base model. This phase aligns the MTP layers with the base model's distribution. Stage 3: Supervised Fine-Tuning * The model was further fine-tuned on synthetic code, math, science, tool calling, instruction following, structured outputs, and general knowledge data. This stage incorporated data designed to support long-range retrieval and multi-document aggregation. Stage 4: Reinforcement Learning * The model underwent multi-environment reinforcement learning using GRPO (Group Relative Policy Optimization) across math, code, science, instruction following, multi-step tool use, multi-turn conversations, and structured output environments. It utilized an asynchronous RL architecture that decouples training from inference and leverages MTP to accelerate rollout generation. * Software used for reinforcement learning: [NeMo RL](https://github.com/NVIDIA-NeMo/RL), [NeMo Gym](https://github.com/NVIDIA-NeMo/Gym) Stage 5: Post-training Quantization (PTQ) * We performed post-training quantization (PTQ) with Nvidia Model Optimizer using the following recipe: Four Over Six NVFP4 (a variant of static MSE calibration) W4A16 on routed and shared experts, FP8 per-tensor dynamic scales on mamba in_proj/out_proj and KV cache. We used a subset of the Nemotron Ultra validation set for calibration with 1000 samples at 32k token length. NVIDIA-Nemotron-3.5-Lightning-30B-A3B-NVFP4 is a result of the above work. - **Input Type(s):** Text - **Input Format(s):** String - **Input Parameters:** One-Dimensional (1D): Sequences - **Other Properties Related to Input:** Maximum context length up to 1M tokens. Supported languages include English, Spanish, French, German, Italian, and Japanese. - **Output Type(s):** Text - **Output Format:** String - **Output Parameters:** One-Dimensional (1D): Sequences - **Other Properties Related to Output:** Maximum context length up to 1M tokens Our AI models are designed and/or optimized to run on NVIDIA GPU-accelerated systems. By leveraging NVIDIA's hardware (e.g. GPU cores) and software frameworks (e.g., CUDA libraries), the model achieves faster training and inference times compared to CPU-only solutions. - **Runtime Engine(s):** PyTorch - **Supported Hardware Microarchitecture Compatibility:** NVIDIA Blackwell; NVIDIA Hopper (NVFP4 / W4A16); NVIDIA Ampere (W4A16) - **Preferred/Supported Operating System(s):** Linux The integration of foundation and fine-tuned models into AI systems requires additional testing using use-case-specific data to ensure safe and effective deployment. Following the V-model methodology, iterative testing and validation at both unit and system levels are essential to mitigate risks, meet technical and functional requirements, and ensure compliance with safety and ethical standards before deployment. * GA (08/11/2026) All deployment snippets below assume: export MODEL_CKPT=nvidia/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-NVFP4 And for DSpark: export DSPARK_CKPT=nvidia/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-NVFP4-DSpark Lightning 3.5 ships with two external draft models for speculative decoding as well as MTP (Multi-Token Prediction). While DSpark is our recommended default (see [Choose your deployment](#choose-your-deployment)), some workloads are better served without speculative decoding, or by DFlash or MTP: * **DSpark:** A semi-autoregressive speculative-decoding drafter that proposes a whole block of candidate tokens in a single forward pass from a parallel backbone. This is recommended for DGX Spark, as well as low-concurrency data centre deployments. * **DFlash:** A speculative-decoding drafter that uses a lightweight block-diffusion model to generate an entire draft block in one forward pass. * **MTP:** A modeling technique that trains the network to predict several future tokens at each position instead of only the next one. **DSpark is the recommended default** for DGX Spark and latency-sensitive, low-concurrency serving. For maximum-throughput batch serving on H100, **no** speculative decoding is fastest. > For more indepth instructions on how to deploy through vLLM, head [here](https://github.com/NVIDIA-NeMo/Nemotron/blob/main/usage-cookbook/Nemotron-3.5-Lightning/vllm_cookbook.ipynb) * vLLM version: `vllm/vllm-openai:v0.27.1` vllm serve --model $MODEL_CKPT \ --moe-backend marlin \ --kv-cache-dtype fp8 \ --enable-prefix-caching \ --gpu-memory-utilization 0.85 \ --speculative_config.num_speculative_tokens 3 \ --mamba-backend flashinfer \ --mamba-cache-mode align \ --reasoning-parser nemotron_v3 \ --speculative_config.model $DSPARK_CKPT \ --tool-call-parser qwen3_coder \ --enable-auto-tool-choice **Validated context:** 1M tokens (default). For max throughput deployments, use the following configuration, no speculative decoding strategy is best for this serving configuration, and due to memory constraints the Mamba cache `dtype` is set as FP16: vllm serve --model $MODEL_CKPT \ --max-num-seqs 256 \ --max-num-batched-tokens 16384 \ --enable-prefix-caching \ --async-scheduling \ --mamba-backend flashinfer \ --moe-backend humming \ --linear-backend humming \ --mamba-ssu-algorithm horizontal \ --mamba-cache-mode align \ --mamba-ssm-cache-dtype float16 \ --enable-mamba-cache-stochastic-rounding \ --mamba-cache-philox-rounds 5 \ --reasoning-parser nemotron_v3 \ --tool-call-parser qwen3_coder \ --enable-auto-tool-choice **Validated context:** 1M tokens (default). For interactive usage scenarios (achieving 40+ TPS/User) use a lower concurrency (<=128) with DSpark: vllm serve --model $MODEL_CKPT \ --max-num-seqs 128 \ --enable-prefix-caching \ --async-scheduling \ --speculative_config.model $DSPARK_CKPT \ --speculative_config.num_speculative_tokens 3 \ --mamba-backend flashinfer \ --mamba-ssm-cache-dtype float16 \ --mamba-cache-mode align \ --enable-mamba-cache-stochastic-rounding \ --mamba-cache-philox-rounds 5 \ --reasoning-parser nemotron_v3 \ --tool-call-parser qwen3_coder \ --enable-auto-tool-choice **Validated context:** 1M tokens, served by default. Lower `--max-model-len` for more KV-cache headroom at high concurrency. For long-context, multi-GPU serving (TP8 with expert parallelism): vllm serve --model $MODEL_CKPT \ --mamba-backend flashinfer \ --async-scheduling \ --enable-prefix-caching \ --mamba-cache-mode align \ --enable-expert-parallel \ --tensor-parallel-size 8 \ --reasoning-parser nemotron_v3 \ --tool-call-parser qwen3_coder \ --enable-auto-tool-choice **Validated context:** 1M tokens (TP8 + expert parallel). vllm serve --model $MODEL_CKPT \ --max-num-batched-tokens 10240 \ --no-enable-prefix-caching \ --async-scheduling \ --speculative_config.model $DSPARK_CKPT \ --speculative_config.num_speculative_tokens 5 \ --mamba-backend flashinfer \ --reasoning-parser nemotron_v3 \ --tool-call-parser qwen3_coder \ --enable-auto-tool-choice **Validated context:** 1M tokens (default). The same checkpoint also serves via W4A16 kernels, extending coverage to Ampere-class GPUs, like the A100 80GB: vllm serve --model nvidia/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-NVFP4 \ --moe-backend humming \ --linear-backend humming \ --max-num-seqs 256 \ --max-num-batched-tokens 32768 \ --enable-prefix-caching \ --async-scheduling \ --quantization modelopt_fp4 \ --mamba-backend flashinfer \ --mamba-cache-mode align \ --mamba-ssu-algorithm simple \ --reasoning-parser nemotron_v3 \ --tool-call-parser qwen3_coder \ --enable-auto-tool-choice **Validated context:** 1M tokens (default) * **Context Length:** The H100 and GB200 snippets above serve the model's full 1M-token context window by default. If you're memory-constrained — or want more KV-cache headroom at high concurrency — lower `--max-model-len` to match your workload. > For more indepth instructions on how to deploy through TensorRT-LLM, head [here](https://github.com/NVIDIA-NeMo/Nemotron/blob/main/usage-cookbook/Nemotron-3.5-Lightning/trtllm_cookbook.ipynb) Container: `nvcr.io/nvidia/tensorrt-llm/release:1.3.0rc24` cat > nemotron-35-lightning-nvfp4-mtp.yaml << EOF kv_cache_config: dtype: fp8 enable_block_reuse: false mamba_state_config: periodic_snapshot_interval: 8192 free_gpu_memory_fraction: 0.8 mamba_ssm_cache_dtype: float16 mamba_ssm_stochastic_rounding: true mamba_ssm_philox_rounds: 5 moe_config: backend: MARLIN nvfp4_gemm_config: allowed_backends: [marlin, cutlass, cublaslt, cuda_core] cuda_graph_config: enable_padding: true max_batch_size: 8 speculative_config: decoding_type: MTP max_draft_len: 3 allow_advanced_sampling: true enable_chunked_prefill: true num_postprocess_workers: 4 print_iter_log: true stream_interval: 10 disable_overlap_scheduler: false EOF trtllm-serve \ $MODEL_CKPT \ --max_batch_size 8 \ --max_num_tokens 8192 \ --reasoning_parser nemotron-v3 \ --tool_parser qwen3_coder \ --config nemotron-35-lightning-nvfp4-mtp.yaml **Validated

Parameters

17.8B

Modality

text->text

License

other

Open source

Yes